Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Jit Yan Lim"'
Publikováno v:
IEEE Access, Vol 12, Pp 86690-86703 (2024)
The few-shot learning paradigm aims to generalize to unseen tasks with limited samples. However, a focus solely on class-level discrimination may fall short of achieving robust generalization, especially when neglecting instance diversity and discrim
Externí odkaz:
https://doaj.org/article/1b1e2b1f1c2d47068e0194e39ab9e5e9
Publikováno v:
IEEE Access, Vol 11, Pp 88099-88115 (2023)
Text-to-image synthesis is a fascinating area of research that aims to generate images based on textual descriptions. The main goal of this field is to generate images that match the given textual description in terms of both semantic consistency and
Externí odkaz:
https://doaj.org/article/45abbef8e7a44dceb9cebd3b9653c704
Publikováno v:
IEEE Access, Vol 11, Pp 39508-39519 (2023)
The task of Text-to-Image synthesis is a difficult challenge, especially when dealing with low-data regimes, where the number of training samples is limited. In order to address this challenge, the Self-Supervision Text-to-Image Generative Adversaria
Externí odkaz:
https://doaj.org/article/5ababde7aa254cb8b7da4faefe7c60f7
Publikováno v:
Pattern Recognition Letters. 169:43-49
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7228a6b1415af9c5cc0e677b02c37af8
https://doi.org/10.1016/j.patrec.2023.03.023
https://doi.org/10.1016/j.patrec.2023.03.023
Publikováno v:
Neurocomputing. 459:327-337
The focus of recent few-shot learning research has been on the development of learning methods that can quickly adapt to unseen tasks with small amounts of data and low computational cost. In order to achieve higher performance in few-shot learning t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a680ce6e3f6b0674aa04abc8174a64d6
https://doi.org/10.1016/j.neucom.2021.06.090
https://doi.org/10.1016/j.neucom.2021.06.090